Noi1r/beamer-skill

A Claude Code skill for creating, compiling, reviewing, and polishing academic Beamer LaTeX presentations. Full lifecycle workflow with quality scoring, pedagogical review, TikZ audit, and more.

What it solves

Beamer Skill provides a structured framework for AI coding assistants to create, compile, and refine academic presentations using Beamer LaTeX. It solves the common problem of AI-generated slides being too dense, lacking pedagogical structure, or failing to meet strict academic formatting and visual standards (such as avoiding overflow and ensuring colorblind-safe contrast).

How it works

The project provides a set of specialized instruction files (skills) that can be integrated into various AI tools like Claude Code, OpenAI Codex CLI, Cursor, and GitHub Copilot. These instructions guide the AI through a multi-phase lifecycle:

  1. Creation: A collaborative process that moves from material analysis and structure planning to drafting and quality loops.
  2. Compilation: A 3-pass XeLaTeX and bibtex process with diagnostics.
  3. Review & Audit: Specialized actions for proofreading, visual layout audits (detecting box overflow), pedagogical validation (using 13 patterns), and TikZ diagram review.
  4. Verification: A numeric quality scoring system that deducts points for issues until a threshold (e.g., 90/100) is met.

It also integrates with pdf-mcp to extract figures directly from research papers for inclusion in slides.

Who it’s for

Researchers, academics, and students who use LaTeX for presentations and want to leverage AI to transform research papers into high-quality, pedagogically sound Beamer slide decks.

Highlights

  • Pedagogical Guardrails: Enforces "motivation before formalism" and strict content density limits (e.g., max 7 bullets per slide).
  • Visual Quality Control: Detects Beamer box overflows and enforces WCAG AA contrast ratios for a colorblind-safe palette.
  • Technical Precision: Mandates the use of \pgfmathsetmacro for TikZ diagrams to avoid hardcoded approximations.
  • Cross-Platform Support: Compatible with Claude Code, Antigravity, Codex CLI, and VS Code extensions (Copilot, Cline, Cursor).
  • Figure Extraction: Ability to pull figures from source PDFs for direct use in LaTeX.
  • PowerPoint Hand-off: A documented workflow to transition a verified Beamer deck into an editable PowerPoint file via Codex Presentations.

Related

  • Project
    luwill/research-skills

    A collection of Claude Code skills designed to automate academic research workflows, including exhaustive literature retrieval, verified proposal writing, and high-fidelity slide generation.

  • Project
    ningzimu/codex-ppt-skill

    An AI agent skill that converts articles, reports, and papers into professional image-based PowerPoint presentations by automating outline planning and visual style generation.

  • Project
    pedrohcgs/claude-code-my-workflow

    A ready-to-fork foundation for AI-assisted academic work that uses specialized agents and quality gates to automate the creation and review of papers, slides, and data analysis.

  • Project
    Yuan1z0825/nature-skills

    A library of reusable research skills for AI agents to automate high-impact academic workflows, from paper reading and Nature-style polishing to peer review simulation and patent drafting.

  • Project
    bahayonghang/academic-writing-skills

    A collection of specialized skills for Claude Code and Codex to polish, audit, and validate academic manuscripts in LaTeX and Typst.